Model comparison
Granite 4.0 H Small vs Qwen2.5 7B Instruct
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.0 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Granite 4.0 H Small scores higher in 4 categories and Qwen2.5 7B Instruct in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.0 H Small leads 31.4 to 12.6.
- The biggest single-benchmark swing is IFEval: 89% for Granite 4.0 H Small and 74.1% for Qwen2.5 7B Instruct.
Side by side
| Granite 4.0 H Small | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 36.5 | 29.0 |
| Released | — | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 19 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.0 H Small: 36.4 (#209), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1249 | — |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Granite 4.0 H Small: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 24.4 (#163), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1240 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.51 |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| Omni-MATH | 29.6% | 29.4% |
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| LMArena Math | 1247 | — |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 32.0 (#215), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| MMLU-Pro | 56.9% | 53.9% |
| GPQA (HELM) | 38.3% | 34.1% |
| GPQA Diamond | — | 35.5% |
| Vectara Hallucination Rate | 5.2% | — |
| LMArena Expert | 1251 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
Granite 4.0 H Small: 38.6 (#228), Qwen2.5 7B Instruct: —
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1249 | — |
| LMArena Russian | 1201 | — |
| LMArena Spanish | 1258 | — |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.7 (#183), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | 89% | 74.1% |
| LMArena Instruction Following | 1222 | — |
Long Context Not comparable
Granite 4.0 H Small: 37.7 (#213), Qwen2.5 7B Instruct: —
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1242 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Granite 4.0 H Small: 43.8 (#227), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Granite 4.0 H Small | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | 73.9% | 73.1% |
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1211 | — |
| LMArena Multi-Turn | 1242 | — |
Frequently asked questions
Is Granite 4.0 H Small better than Qwen2.5 7B Instruct?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 29.0 on the Noometry Index.
Is Granite 4.0 H Small or Qwen2.5 7B Instruct better for coding?
They score almost the same on coding (36.4 vs 36.5); test both on your own repository before choosing.
How many benchmarks do Granite 4.0 H Small and Qwen2.5 7B Instruct share?
5 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Qwen2.5 7B Instruct has 15.